One thought on this - could we make the API have a "which" parameter
that indicates the type of thing being acted upon? E.g., like
sys_setpriority(), which can specify the target as a process, a pgrp
or a user.

Right now the target would just be a process, but I'd really like the
ability to be able to specify an fd on a cgroup directory to indicate
that I want the child to inherit from that cgroup's namespaces. That
way you wouldn't need to keep a child process alive in the namespace
just to act as a hijack target.

Paul

On 10/9/07, Serge E. Hallyn <serue@us.ibm.com> wrote:
> >From 945fe66259cd0cfdc2fe846287b7821e329a558c Mon Sep 17 00:00:00 2001
> From: sergeh@us.ibm.com <hallyn@kernel.(none)>
> Date: Tue, 9 Oct 2007 08:30:30 -0700
> Subject: [PATCH] namespaces: introduce sys_hijack (v4)
>
> Move most of do_fork() into a new do_fork_task() which acts on
> a new argument, task, rather than on current.  do_fork() becomes
> a call to do_fork_task(current, ...).
>
> Introduce sys_hijack (for x86 only so far).  It is like clone, but
>  in place of a stack pointer (which is assumed null) it accepts a
> pid.  The process identified by that pid is the one which is
> actually cloned.  Some state - include the file table, the signals
> and sighand (and hence tty), and the ->parent are taken from the
> calling process.
>
> The effect is a sort of namespace enter.  The following program
> uses sys_hijack to 'enter' all namespaces of the specified pid.
> For instance in one terminal, do
>
>         mount -t cgroup -ons /cgroup
>         hostname
>           qemu
>         ns_exec -u /bin/sh
>           hostname serge
>           echo $$
>             1073
>           cat /proc/$$/cgroup
>             ns:/node_1073
>
> In another terminal then do
>
>         hostname
>           qemu
>         cat /proc/$$/cgroup
>           ns:/
>         hijack 1073
>           hostname
>             serge
>           cat /proc/$$/cgroup
>             ns:/node_1073
>
> sys_hijack is arch-dependent and is only implemented for i386 so far.
>
> Changelog:
>         Aug 23: send a stop signal to the hijacked process
>                 (like ptrace does).
>         Oct 09: Update for 2.6.23-rc8-mm2 (mainly pidns)
>                 Don't take task_lock under rcu_read_lock
>                 Send hijacked process to cgroup_fork() as
>                 the first argument.
>                 Removed some unneeded task_locks.
>
> ==============================================================
> hijack.c
> ==============================================================
>
> int do_clone_task(void)
> {
>         execl("/bin/sh", "/bin/sh", NULL);
> }
>
> int main(int argc, char *argv[])
> {
>         int pid;
>         int ret;
>         int status;
>
>         if (argc < 2)
>                 return 1;
>         pid = atoi(argv[1]);
>
>         ret = syscall(327, SIGCHLD, pid, NULL, NULL);
>
>         if  (ret == 0) {
>                 return do_clone_task();
>         } else if (ret < 0) {
>                 perror("sys_hijack");
>         } else {
>                 printf("waiting on cloned process %d\n", ret);
>                 while (waitpid(ret, &status, __WCLONE) != ret);
>                 printf("cloned process %d exited with %d\n", ret, status);
>         }
>
>         return ret;
> }
> ==============================================================
>
> Signed-off-by: Serge Hallyn <serue@us.ibm.com>
> ---
>  arch/i386/kernel/process.c       |   58 ++++++++++++++++++++++++++++++-
>  arch/i386/kernel/syscall_table.S |    1 +
>  arch/s390/kernel/process.c       |   12 +++++-
>  include/asm-i386/unistd.h        |    3 +-
>  include/linux/cgroup.h           |    5 ++-
>  include/linux/pid.h              |    2 +-
>  include/linux/ptrace.h           |    1 +
>  include/linux/sched.h            |    2 +
>  include/linux/syscalls.h         |    1 +
>  kernel/cgroup.c                  |    8 ++--
>  kernel/fork.c                    |   69 +++++++++++++++++++++++++++----------
>  kernel/pid.c                     |    5 ++-
>  kernel/ptrace.c                  |    7 ++++
>  13 files changed, 141 insertions(+), 33 deletions(-)
>
> diff --git a/arch/i386/kernel/process.c b/arch/i386/kernel/process.c
> index bfcd01e..01f4d16 100644
> --- a/arch/i386/kernel/process.c
> +++ b/arch/i386/kernel/process.c
> @@ -455,8 +455,15 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
>         unsigned long unused,
>         struct task_struct * p, struct pt_regs * regs)
>  {
> +       return copy_a_thread(current, nr, clone_flags, esp, unused,
> +               p, regs);
> +}
> +
> +int copy_a_thread(struct task_struct *tsk, int nr, unsigned long clone_flags,
> +       unsigned long esp, unsigned long unused,
> +       struct task_struct * p, struct pt_regs * regs)
> +{
>         struct pt_regs * childregs;
> -       struct task_struct *tsk;
>         int err;
>
>         childregs = task_pt_regs(p);
> @@ -471,7 +478,6 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long esp,
>
>         savesegment(gs,p->thread.gs);
>
> -       tsk = current;
>         if (unlikely(test_tsk_thread_flag(tsk, TIF_IO_BITMAP))) {
>                 p->thread.io_bitmap_ptr = kmemdup(tsk->thread.io_bitmap_ptr,
>                                                 IO_BITMAP_BYTES, GFP_KERNEL);
> @@ -783,6 +789,54 @@ asmlinkage int sys_clone(struct pt_regs regs)
>         return do_fork(clone_flags, newsp, &regs, 0, parent_tidptr, child_tidptr);
>  }
>
> +asmlinkage int sys_hijack(struct pt_regs regs)
> +{
> +       unsigned long clone_flags;
> +       int __user *parent_tidptr, *child_tidptr;
> +       pid_t pid;
> +       struct task_struct *task;
> +       int ret = -EINVAL;
> +
> +       clone_flags = regs.ebx;
> +       pid = regs.ecx;
> +       parent_tidptr = (int __user *)regs.edx;
> +       child_tidptr = (int __user *)regs.edi;
> +
> +       rcu_read_lock();
> +       task = find_task_by_vpid(pid);
> +       if (task)
> +               get_task_struct(task);
> +       rcu_read_unlock();
> +
> +       if (task) {
> +               task_lock(task);
> +               put_task_struct(task);
> +       }
> +
> +       if (task) {
> +               if (!ptrace_may_attach_locked(task)) {
> +                       ret = -EPERM;
> +                       goto out_put_task;
> +               }
> +               if (task->ptrace) {
> +                       ret = -EBUSY;
> +                       goto out_put_task;
> +               }
> +               force_sig_specific(SIGSTOP, task);
> +
> +               task_unlock(task);
> +               ret = do_fork_task(task, clone_flags, regs.esp, &regs, 0,
> +                       parent_tidptr, child_tidptr);
> +               wake_up_process(task);
> +               task = NULL;
> +       }
> +
> +out_put_task:
> +       if (task)
> +               task_unlock(task);
> +       return ret;
> +}
> +
>  /*
>   * This is trivial, and on the face of it looks like it
>   * could equally well be done in user mode.
> diff --git a/arch/i386/kernel/syscall_table.S b/arch/i386/kernel/syscall_table.S
> index df6e41e..495930c 100644
> --- a/arch/i386/kernel/syscall_table.S
> +++ b/arch/i386/kernel/syscall_table.S
> @@ -326,3 +326,4 @@ ENTRY(sys_call_table)
>         .long sys_fallocate
>         .long sys_revokeat              /* 325 */
>         .long sys_frevoke
> +       .long sys_hijack
> diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
> index 70c5737..f256e7a 100644
> --- a/arch/s390/kernel/process.c
> +++ b/arch/s390/kernel/process.c
> @@ -223,6 +223,14 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
>         unsigned long unused,
>          struct task_struct * p, struct pt_regs * regs)
>  {
> +       return copy_a_thread(current, nr, clone_flags, new_stackp, unused,
> +                                p, regs);
> +}
> +
> +int copy_a_thread(struct task_struct *task, int nr, unsigned long clone_flags,
> +       unsigned long new_stackp, unsigned long unused,
> +        struct task_struct * p, struct pt_regs * regs)
> +{
>          struct fake_frame
>            {
>             struct stack_frame sf;
> @@ -251,8 +259,8 @@ int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
>          * save fprs to current->thread.fp_regs to merge them with
>          * the emulated registers and then copy the result to the child.
>          */
> -       save_fp_regs(&current->thread.fp_regs);
> -       memcpy(&p->thread.fp_regs, &current->thread.fp_regs,
> +       save_fp_regs(&task->thread.fp_regs);
> +       memcpy(&p->thread.fp_regs, &task->thread.fp_regs,
>                sizeof(s390_fp_regs));
>          p->thread.user_seg = __pa((unsigned long) p->mm->pgd) | _SEGMENT_TABLE;
>         /* Set a new TLS ?  */
> diff --git a/include/asm-i386/unistd.h b/include/asm-i386/unistd.h
> index 006c1b3..fe6eeb4 100644
> --- a/include/asm-i386/unistd.h
> +++ b/include/asm-i386/unistd.h
> @@ -332,10 +332,11 @@
>  #define __NR_fallocate         324
>  #define __NR_revokeat          325
>  #define __NR_frevoke